ShoheiAI/luye-yuanXL

Luye Yuan (aka KanoM) Style

Prompt

score_9, score_8_up, score_7_up, score_6_up, source_anime, pink background, white border, 1boy, solo, young, brown hair, purple eyes, smile, japanese clothes, yukata, smiling, upper body, mask on top of head <lora:luye-yuan_PDXL_v2-ShoAI:1>

Negative Prompt

bara, source_pony, (hands:1.2)

Prompt

score_6, score_6_up, solo, white background, film grain, muted colors, full body, from below, 1boy, young, brown hair, red eyes, gym uniform, red shorts, black bike shorts, red headband, standing, foot up, sneakers <lora:luye-yuan_PDXL_v2-ShoAI:1>

Negative Prompt

bara, source_pony, (hands:1.2)

Model description

This LORA is designed to recreate the style of the artist Luye Yuan (aka KanoM, aka Mootee, aka Shika Muro). No trigger words needed, but read the description of the score tags for details. This LORA is slightly experimental since I trained it using the multiple resolution feature of OneTrainer at 1024, 1152, and 1280 resolutions. This may result in some visual artifacting during normal generation (at least it did using Forge), but this is fixed using a Hires Fix pass. I have also included an older v1 of this LORA that was trained only at 1024 resolution and may produce better results when not using Hires Fix.

Please support the original artist wherever possible so they can continue to produce their art. Without them, LORAs such as these would not be possible.

This model is also available on TensorArt and CivitAI: https://tensor.art/models/743721648257213339/Luye-Yuan-(aka-KanoM)-Style-v2 https://civitai.com/models/501393/luye-yuan-aka-kanom-style?modelVersionId=557504

USAGE NOTES:

Recommended to be used at 0.9 strength. The style is mostly going to affect characters since most of the images in the dataset have simple backgrounds.

This LORA was trained on the base Pony Diffusion v6, but best results will come from using AutismMix.

NOTE: While not intended for this use, the training dataset contains many NSFW images. If you do not want NSFW, make sure you actively prompt away from it. For this pass, images were not tagged with rating_safe, rating_explicit, etc.

TAGGING NOTES:

V2 of this LORA was trained on base Pony Diffusion and images were ranked in scores 6-9 as well as given the "source_anime" tag. This artist likes to put lots of bandaids and bandages on their characters, so you may need to put "bandaid" or "bandage" in the negative. There are also many characters in the dataset with animal features that may pop up unprompted on occasion.

Score 9 and 8 are the most recent works with a slight 2.5d look to them.

Score 7 are works that are a bit flatter in appearance or not as detailed.

Score 6 is entirely works that are a very flat 2D style with muted colors. You may want to put "muted colors" in the negative if you are seeing undesired color shifts.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.